A fine-tuned "cat obsession" as a control for AI welfare criteria: every probe criterion passes, and a relief button tracks how a drive is delivered, not whether it's active [R]
I fine-tuned Qwen3.5-4B so every answer comes back to cats. The cat obsession is in the weights. (It's live, you can poke it until Nov 1 cat4b.mirrorethic.com Then I ran the test that recent AI-welfare papers use which…
Discussion
Rejoignez la communauté pour réagir et poser vos questions.
Aucun message pour l'instant. Lancez la discussion !